Evaluation of Feature Selection Methods in Estimation of Precipitation Based on Deep Learning Artificial Neural Networks
Mohammad Taghi Sattari, · Anca Avram, · Halit Apaydin, · Oliviu Matei

Abstract. Precipitation is the most important element of the water cycle and an indispensable element of water resources management. This paper’s aim is to model the monthly precipitation in 8 precipitation observation stations in the province of Hamadan, Iran. The effects and role of different feature weights pre-processing methods (Weight by deviation, Weight by PCA, Weight by correlation, and Weight by Support Vector Machine) on artificial intelligence modeling were investigated. Deep learning methods were applied based on a multi-layer feed-forward artificial neural network that is trained with Stochastic Gradient Descent using back-propagation (DL-SGD) and Convolutional Neural Networks (CNN) modeling. The precipitation of each station is modeled using the precipitation values of the other stations. The best result, among all scenarios, at the Vasaj station according to the DL-SGD method (CC=0.9845, NS=0.9543, and RMSE=10.4169 mm) and at the Varayineh station according to the CNN method (CC=0.9679, NS=0.9362, and RMSE=16.0988 mm) were estimated.

Keywords: Precipitation, Artificial intelligence, Feature selection, Deep learning, Stochastic gradient descent, Feature weights, H2O cluster.

Other publications